refactor(ai): address PR #176 review — finite-timeout wording, env doc, tests, permanent provider-http module

- Wording: every comment now says the stream timeouts are RAISED to a
  generous-but-finite ~15-min silence timeout, not "disabled (0)" (the stale
  comments contradicted the code, which uses AI_STREAM_TIMEOUT_MS, default
  900000ms).
- Architecture (the load-bearing-temporary trap): the streaming fetch reached
  the chat provider only by riding the "temporary DIAGNOSTIC" telemetry, so
  deleting the telemetry by its own label would silently revert the timeout fix.
  Legitimize it: rename ai-http-diagnostics.ts -> ai-provider-http.ts,
  createDiagnosticFetch -> createInstrumentedFetch, field aiDiagnosticFetch ->
  aiProviderFetch, drop the "temporary" labels, and document the chat transport
  (streaming fetch + instrumentation) as one intentional construct.
- Docs: AI_STREAM_TIMEOUT_MS added to .env.example next to AI_EMBEDDING_TIMEOUT_MS.
- Tests:
  - ai-provider-http.spec: createInstrumentedFetch delegates to the injected
    baseFetch with the same input/init, returns the Response untouched, rethrows
    the error, and defaults to global fetch — covering the baseFetch seam.
  - ai-streaming-fetch.spec: the delayed-server test is now LOAD-BEARING — with
    AI_STREAM_TIMEOUT_MS set below the 1.5s server delay the call actually rejects
    (a lost dispatcher -> global 300s default would NOT), proving the configured
    dispatcher is wired; plus the default-timeout happy path.

server tsc clean; ai-streaming-fetch / ai-provider-http / ai.service / mcp-servers
/ ai-error specs green (41).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.env.example

@@ -136,6 +136,12 @@ MCP_DOCMOST_PASSWORD=
 # A slow/hung embeddings endpoint fails after this and the batch continues.
 # AI_EMBEDDING_TIMEOUT_MS=120000
 
+# Silence timeout (ms) for streaming chat/agent AI calls AND external-MCP traffic.
+# Bounds time-to-first-byte and the gap BETWEEN chunks (NOT the total turn length),
+# so an arbitrarily long turn that keeps streaming is never cut. Finite so a hung
+# provider is eventually broken instead of leaking forever. Default 900000 (15 min).
+# AI_STREAM_TIMEOUT_MS=900000
+
 # --- Anonymous public-share AI assistant ---
 # Opt-in per workspace (AI settings -> "public share assistant"; off by default).
 # When enabled, anonymous visitors of a published share can ask an AI about that